pneuma
An OS where software materializes from a prompt
What it does
Pneuma is a desktop computing environment with no pre-installed applications. You describe what you need and a working program appears in seconds. Want a CPU monitor? A game? A data visualizer? Just type it. Under the hood, your prompt generates a Rust program that compiles to WebAssembly and runs in a GPU-rendered sandbox (Vulkan/Metal/DX12). Agents persist, communicate with each other via IPC, and can be shared through a community store.
Does the same job
all alternatives →- IBI built an OS that is pure AIMar 2026 · pneuma.computer · ▲34
I've been building Pneuma, a desktop computing environment where software doesn't need to exist before you need it. There are no pre-installed applications. You boot to a blank screen with a prompt. You describe what you want: a CPU monitor, a game, a notes app, a data visualizer and a working program materializes in seconds. Once generated, agents persist. You can reuse them, they can communicate with each other through IPC, and you can share them through a community agent store. The idea isn't that everything is disposable. It's that creation is instant and the barrier to having exactly…
- PFPneumatic – free open-source workflow software2024 · github.com · ▲63
Hi HN, I'm one of the co-founders of Pneumatic, an enterprise-grade workflow software designed for small, fast-growing startups. Yesterday, we released Pneumatic under the Apache 2.0 license. If your team has used Trello, Basecamp, or Asana before and you're now looking to implement a more structured, mature approach by building repeatable task sequences, you should try Pneumatic. Here's what Pneumatic offers: - Task sequences defined by templates. Design a template once and run multiple instances of a process based on this reusable template—manually, via API, or with a public share kick-off…
- ADA DOS-like hobby OS written in Rust and x86 assembly2025 · github.com · ▲207
To try it out, simply build the project yourself from source, or use attached bootable ISO image of the system (in Releases on Github) and run it in QEMU. https://blog.vxn.dev/rou2exos-rusted-edition
- AAAmbient, a multiplayer game engine and platform using WASM/WebGPU/Rust2023 · ambient.run · ▲90
Earlier this year, we released our open-source game engine [0] built with Rust, WebAssembly, and WebGPU. Today, we’re happy to announce the Ambient platform, which brings web deployment, server hosting, and more to the runtime. With Ambient, you can make a game, deploy it to the browser in one command, share your URL and instantly play with others, no downloads or installs needed. Our WASM use is innovative; it is being used as both a sandboxed runtime for user code, and as a way to run the entire Ambient runtime in the browser. This, paired with our ECS data model, enables a highly modular…
- HGHorizon – GPU-accelerated infinite-canvas terminal in RustMar 2026 · github.com · ▲84
Tabs, splits, and tmux work fine until you have several projects open with logs, tests, and long-running shells. I kept rebuilding context instead of resuming work. Horizon puts shells on an infinite canvas. You can arrange them into workspaces and reopen later with layout, scrollback, and history intact. Built in 3 days with Claude/Codex, dogfooding the workflow as I went. Feedback and contributions welcome.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app